Yuksel Arslantas
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yuksel Arslantas has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Ege Yuceel
Department of Electrical and Electronics Engineering, Bilkent University, Ankara, Trkiye
2 shared publications - Muhammed Omer Sayin
Department of Electrical and Electronics Engineering, Bilkent University, Ankara, Trkiye
2 shared publications - Yigit Yalin
Department of Computer Engineering, Bilkent University, Ankara, Trkiye
1 shared publication
Latest Publications
- 2 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 70 (11) , 7523-7537
Convergence of Heterogeneous Learning Dynamics in Zero-Sum Stochastic Games
In this article, we present new families of algorithms for the repeated play of two-agent (near) zero-sum games and two-agent zero-sum stochastic games. For example, the family includes fictitious play and its variants as members. Commonly, the algorithms in this family are all uncoupled, rational, and convergent even in heterogeneous cases, e.g., where the dynamics may differ in terms of learning rates, full, none or temporal access to opponent actions, and model-based versus model-free learning. The convergence of heterogeneous dynamics is of practical interest especially in competitive environments since agents may have no means or interests in following the same dynamic with the same parameters. We prove that any mixture of such asymmetries does not impact the algorithms’ convergence to equilibrium (or near equilibrium if there is experimentation) in zero-sum games with repeated play and in zero-sum (irreducible) stochastic games with sufficiently small discount factors.
- 2 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 70 (11) , 7523-7537
Convergence of Heterogeneous Learning Dynamics in Zero-Sum Stochastic Games
In this article, we present new families of algorithms for the repeated play of two-agent (near) zero-sum games and two-agent zero-sum stochastic games. For example, the family includes fictitious play and its variants as members. Commonly, the algorithms in this family are all uncoupled, rational, and convergent even in heterogeneous cases, e.g., where the dynamics may differ in terms of learning rates, full, none or temporal access to opponent actions, and model-based versus model-free learning. The convergence of heterogeneous dynamics is of practical interest especially in competitive environments since agents may have no means or interests in following the same dynamic with the same parameters. We prove that any mixture of such asymmetries does not impact the algorithms’ convergence to equilibrium (or near equilibrium if there is experimentation) in zero-sum games with repeated play and in zero-sum (irreducible) stochastic games with sufficiently small discount factors.
- 18 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems Letters
- Vol. 8, 1733-1738
Strategizing Against Q-Learners: A Control-Theoretical Approach
In this paper, we explore the susceptibility of the independent Q-learning algorithms (a classical and widely used multi-agent reinforcement learning method) to strategic manipulation of sophisticated opponents in normal-form games played repeatedly. We quantify how much strategically sophisticated agents can exploit naive Q-learners if they know the opponents’ Q-learning algorithm. To this end, we formulate the strategic actors’ interactions as a stochastic game (whose state encompasses Q-function estimates of the Q-learners) as if the Q-learning algorithms are the underlying dynamical system. We also present a quantization-based approximation scheme to tackle the continuum state space and analyze its performance for two competing strategic actors and a single strategic actor both analytically and numerically.
- 18 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems Letters
- Vol. 8, 1733-1738
Strategizing Against Q-Learners: A Control-Theoretical Approach
In this paper, we explore the susceptibility of the independent Q-learning algorithms (a classical and widely used multi-agent reinforcement learning method) to strategic manipulation of sophisticated opponents in normal-form games played repeatedly. We quantify how much strategically sophisticated agents can exploit naive Q-learners if they know the opponents’ Q-learning algorithm. To this end, we formulate the strategic actors’ interactions as a stochastic game (whose state encompasses Q-function estimates of the Q-learners) as if the Q-learning algorithms are the underlying dynamical system. We also present a quantization-based approximation scheme to tackle the continuum state space and analyze its performance for two competing strategic actors and a single strategic actor both analytically and numerically.